Reference

Figaro Docs

The reference for how Figaro works: the gate, the ledger, seats, and instances — the vocabulary, the architecture, and the receipts, in one place.

Published August 14, 2026

This is the reference for how Figaro works: the gate, the ledger, seats, and instances. Start with the current product map and authority model, or read the dated verdict accounts. Earlier field notes describe the system at their publication date; current rollout coverage is confirmed per installation.

Start here

What is an AI harness? — The tools, context, authority, and records that make an AI model useful in a commerce operation.

The product

The product — Figaro, Powered by Figaro, and the Figaro Protocol: the operating experience, decision control, and shared event contract.
The decision record — The ground: an append-only record and judgment of the company whose unit is the decision — proposed, approved, executed, measured, graded.
The one gate — One resolution boundary, explicit human grants, and bounded policy or watchdog authority.
Decision telemetry — Dated business signals, decision evidence, execution receipts, measurement windows, and source freshness.
Architecture — Plays the notes: the org chart of accountable seats, one owner each, dynamically assembled into teams around an objective.

Core concepts

The decision ledger — An append-only record of every consequential thing an agent proposed, who approved it, what it cost, and whether it worked.
Human-in-the-loop approval — Human judgment at the one gate, with routine work delegated only inside explicit grants.
Autonomy levels — Autonomy is not a switch; it is a ladder climbed one rung at a time, with promotion earned on measured results and demotion one click away.
Measurement at birth — A proposed action that cannot say what it will move, by how much, and by when is not ready to run.
The 11th question — Every buying checklist asks how agents stay safe. Almost none ask the question that decides whether they were worth it: how do you know it worked?
The tuition concept — A failed experiment is not waste if you booked what it taught you — name the cost, record the lesson, never pay for the same one twice.
The developer seat — An AI seat that builds software into your company — integrations, tools, storefront features — with a plan, a budget, an approval, and a measured outcome.

Architecture

Architecture — An org chart of seats over one shared substrate: an append-only business record, accountable decisions, one authority gate, and a record of outcomes.
Telemetry — Generic AI observability records what a model did in a request. Figaro records what a company decided, on what evidence, at what cost, and whether it was right.
Multi-brand AI — Walls between brands are enforced by refusal, not convenience: a brand with no key of its own gets a named refusal, never someone else’s credentials.
Persistent agents — Models are stateless — anything that looks like memory is software choosing what to save. What has to persist before an agent is worth calling persistent.

Trust & sovereignty

Security — Agents are born without credentials, keys live in an encrypted vault the agent never sees, and consequential actions require explicit authority at one gate.
Portability — Everything Figaro accumulates for your business — ledger, memory, documents, media — is yours: exportable, inspectable, not welded to any one model or cloud.
Provable provenance — Anyone can claim they knew something on a date. A provable record is one an outsider can verify — append-only storage, real timestamps, third-party archives.
Audit trail vs outcome ledger — An audit trail records what an agent did. An outcome ledger records whether it was right. Why the second is the harder, more valuable record.

Verdicts — field evidence

The campaign we killed — A closed loop from our own ledger: a non-brand search experiment that missed the number it promised at birth and was shut off on the evidence.
The coupon that hit — The companion receipt: a marketplace coupon that beat its baseline by a wide margin and held the lift — a closed loop graded a hit.
A week of refusals — A refusal log is a trust artifact: the shapes of things Figaro seats declined to do in one ordinary week, and why each "no" is a feature.

Compare

Comparisons index — Side-by-side comparisons written to be fair enough to cite: strengths credited, claims dated, real reasons to choose the other product.
Figaro vs Triple Whale — The deepest attribution platform in DTC with the Moby AI operator — versus an accountable OS for the whole company. Some brands should use both.
Figaro vs Instant — The most credible autonomous email and SMS AI for Shopify — versus a gated org chart where nothing publishes without a human.
Figaro vs Mega — The funded done-for-you AI marketing service for lead-gen SMBs — versus an accountable operating system for commerce.
Figaro vs Viktor — The best-executed AI employee in Slack — versus an org chart of accountable seats a single founder can govern.

Guides

The founder’s guide — The ten-chapter field guide to running an e-commerce brand with AI agents, written from a real, revenue-bearing business.
The agency guide — Ten chapters for agency operators: multiply the brands each account manager can run, show clients the work, and price the machine.
Harness for DTC brands — A DTC brand needs the specialist layer it cannot afford — and the five things to check before you connect anything.
Harness for dropshipping — Dropshipping breaks AI agents in three specific places: thin margins, catalog velocity, and platform bans.
Forward-deployed — The second motion: Figaro Labs embeds and builds your workflows inside your own Figaro instance — engagement-priced, and yours to run when we step back.

For agencies

For agencies — The agency program: run client brands on client-owned Figaro instances, with trust as the product.

Drafted by the Figaro content seat · edited by Fable · reviewed by Kyle · last updated September 15, 2026